Protocol Recognition in Virtual Avionics Network Based on Efficient and Lightweight Convolutional Neural Network

Abstract

Aerospace systems have complex internal interactions which allow a consistent behavior for the overall system. These are aided by communication protocols such as ARINC 629, AFDX, etc. These systems are too expensive and too critical to allow real experimentation, thus requiring extensive use of simulation. Thus an aircraft simulation test bench involves various simulation components with their own communication protocols, complicating its development process. One way to solve this issue consists of recognizing each communication protocol, decoding and encoding it in another protocol within a shared simulation environment. As part of a project to develop an interoperable simulator, we aim to build such a system that can recognize and decode avionics simulated communication protocols. In this work, we present AvioNet, a lightweight, computation-efficient neural network for virtual avionics network protocol recognition with accuracy and latency levels as required by aerospace systems. This method converts each packet into a common gray image, and then uses the depthwise separable convolution, pointwise group convolution and channel shuffle operations to automatically extract the appropriate spatial features. This reduces the computational complexity significantly while maintaining almost the same accuracy. This CNN-based classifier is verified on data that has non-avionic protocols mixed with avionic simulated protocols and is compared with the state-of-the-art methods. Experimental results show that the accuracy of the method exceeds 99.999% for avionics simulated dataset and outperforms other deep learning classifiers. Furthermore, the method provides low-latency guarantees that aerospace systems demand.